P
US10990809B2ActiveUtilityPatentIndex 40

Computer-implemented method and program product for object identification from image data

Assignee: IDEMIA IDENTITY & SECURITY GERMANY AGPriority: May 2, 2018Filed: May 2, 2019Granted: Apr 27, 2021
Est. expiryMay 2, 2038(~11.8 yrs left)· nominal 20-yr term from priority
Inventors:BEHRENBERG CHRISTIANFUHRMANN STEFANKRUEGER MAXIMILIANSCHLENGER STEFANWERNER MARTINWINTER CHRISTIANWÖRMANN MARCOZHOU RAN
G06F 16/784G06V 10/768G06V 40/172G06V 20/52G06V 20/40G06T 7/70G06T 2207/30201G06K 9/00288G06K 9/00711G06K 9/00771
40
PatentIndex Score
0
Cited by
9
References
18
Claims

Abstract

The present invention relates to a computer-implemented method of identifying a physical object, comprising the steps of providing image data comprising an image object representing a physical object, analyzing the image data to extract identification data for the image object, providing supplementary data associated with a particular physical object, and determining whether the image object corresponds to the particular physical object based on the identification data and supplementary data.

Claims

exact text as granted — not AI-modified
The invention claimed is: 
     
       1. A computer-implemented method of identifying a physical object executed by one or more processing devices and, comprising the steps of:
 providing image data comprising an image object representing a physical object; 
 analyzing the image data to extract identification data for the image object; 
 providing supplementary data associated with a particular physical object; 
 determining whether the image object corresponds to the particular physical object based on the identification data and supplementary data; 
 wherein determining whether the image object corresponds to the particular physical object comprises determining a candidate object without using the supplementary data and verifying that the candidate object corresponds to the particular physical object using the supplementary data; and wherein
 a) determining the candidate object comprises determining that the image object corresponds to the candidate object with a first probability exceeding a first probability threshold; and 
 b) verifying that the candidate object corresponds to the particular physical object comprises determining based on the supplementary data that the candidate object corresponds to the particular physical object with a second probability exceeding a second probability threshold that is higher than at least one selected from the group comprising the first probability and the first probability threshold. 
 
 
     
     
       2. The computer-implemented method according to  claim 1 , wherein providing the image data comprises recording video data and providing at least one video frame of the recorded video data. 
     
     
       3. The computer-implemented method according to  claim 2 , wherein analyzing the image data and recording the video data are performed in real time. 
     
     
       4. The computer-implemented method according to  claim 1 , wherein the particular physical object is a person or a face of a person. 
     
     
       5. The computer-implemented method according to  claim 1 , wherein providing the supplementary data comprises providing data from social media or a device connected to the Internet or another network as an intranet. 
     
     
       6. The computer-implemented method according to  claim 1 , wherein providing the supplementary data comprises providing another identification data for another physical object associated with the particular physical object. 
     
     
       7. The computer-implemented method according to  claim 6 , wherein the other physical object associated with the particular physical object is one of a person, a vehicle, a bag, a cap, a helmet, a shoe, a garment, a weapon and a mobile device. 
     
     
       8. The computer-implemented method according to  claim 6 , further comprising recognizing the other physical object in the analyzed image data. 
     
     
       9. The computer-implemented method according to  claim 1 , wherein determining whether the image object corresponds to the particular physical object comprises determining a probability measure of a matching of the image object with the particular physical object and further comprising determining that the image object corresponds to the particular physical object, if the determined probability measure exceeds a predetermined threshold. 
     
     
       10. The computer-implemented method according  claim 9 , wherein determining the probability measure comprises matching the image object with the particular physical object by comparing the identification data with pre-stored data of the particular physical object. 
     
     
       11. The computer-implemented method according to  claim 1 , wherein analyzing the image data comprises employing a face recognition procedure comprising extracting jets from the image data. 
     
     
       12. The computer-implemented method according to  claim 1 , further comprising displaying a portion of the image data based on the result of the step of determining whether the image object corresponds to the particular physical object. 
     
     
       13. The computer-implemented method according to  claim 2 , wherein the particular physical object is a person or a face of a person. 
     
     
       14. The computer-implemented method according to  claim 3 , wherein the particular physical object is a person or a face of a person. 
     
     
       15. The computer-implemented method according to  claim 1 , wherein providing the supplementary data comprises at least one selected from the group of (i) providing data from social media or a device connected to the Internet or another network as an intranet and (ii) providing another identification data for another physical object associated with the particular physical object. 
     
     
       16. The computer-implemented method according to  claim 2 , wherein providing the supplementary data comprises at least one selected from the group of (i) providing data from social media or a device connected to the Internet or another network as an intranet and (ii) providing another identification data for another physical object associated with the particular physical object. 
     
     
       17. The computer-implemented method according to  claim 3 , wherein providing the supplementary data comprises at least one selected from the group of (i) providing data from social media or a device connected to the Internet or another network as an intranet and (ii) providing another identification data for another physical object associated with the particular physical object. 
     
     
       18. A computer program product, comprising one or more non-transitory computer readable media having computer-executable instructions for performing the steps of a computer-implemented method comprising:
 providing image data comprising an image object representing a physical object; 
 analyzing the image data to extract identification data for the image object; 
 providing supplementary data associated with a particular physical object; 
 determining whether the image object corresponds to the particular physical object based on the identification data and supplementary data; 
 wherein determining whether the image object corresponds to the particular physical object comprises determining a candidate object without using the supplementary data and verifying that the candidate object corresponds to the particular physical object using the supplementary data; and wherein
 a) determining the candidate object comprises determining that the image object corresponds to the candidate object with a first probability exceeding a first probability threshold; and 
 b) verifying that the candidate object corresponds to the particular physical object comprises determining based on the supplementary data that the candidate object corresponds to the particular physical object with a second probability exceeding a second probability threshold that is higher than at least one selected from the group comprising the first probability and the first probability threshold.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.